{"mean_reward": 589.5, "std_reward": 136.71960356876406, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-04T00:25:35.650685"} |
{"mean_reward": 589.5, "std_reward": 136.71960356876406, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-04T00:25:35.650685"} |